English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Reinforcement Learning (RL) plays an important role in the roboticmanipulation domain since it allows self-learning from trial-and-errorinteractions with the environment. Still, sample efficiency and rewardspecification seriously limit its potential. One possible solution involveslearning from expert guidance. However, obtaining a human expert is impracticaldue to the high cost of supervising an RL agent, and developing an automaticsupervisor is a challenging endeavor. Large Language Models (LLMs) demonstrateremarkable abilities to provide human-like feedback on user inputs in naturallanguage. Nevertheless, they are not designed to directly control low-levelrobotic motions, as their pretraining is based on vast internet data ratherthan specific robotics data. In this paper, we introduce the Lafite-RL(Language agent feedback interactive Reinforcement Learning) framework, whichenables RL agents to learn robotic tasks efficiently by taking advantage ofLLMs' timely feedback. Our experiments conducted on RLBench tasks illustratethat, with simple prompt design in natural language, the Lafite-RL agentexhibits improved learning capabilities when guided by an LLM. It outperformsthe baseline in terms of both learning efficiency and success rate,underscoring the efficacy of the rewards provided by an LLM.

Accelerating Reinforcement Learning of Robotic Manipulations via Feedback from Large Language Models